EUVIMEDEUVIMED entdecken
Crossref

wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation

Benjamin Hawks, Jason Weitz, Dmitri Demler, Karla Tame-Narvaez, Dennis Plotnikov, Mohammad Mehdi Rahimifar, Hamza Ezzaoui Rahali, Audrey C. Therrien, Donovan Sproule, Elham E. Khoda, Keegan A. Smith, Russell Marroquin und 4 weitere

ACM Transactions on Reconfigurable Technology and Systems · 30.06.2026 · 19 (2) · 1-29

DOI: 10.1145/3787490 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Reconfigurable Technology and Systems, online erschienen am 27.05.2026. Verfasst von Benjamin Hawks und 15 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: U.S. Department of Energy, Office of Science, Office of High Energy Physics, U.S. Department of Energy, Office of Science, Office of Workforce Development for Teachers and Scientists (WDTS), Science Undergraduate Laboratory Internships…, National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As machine learning (ML) is increasingly implemented in hardware to address real-time challenges in scientific applications, the development of advanced toolchains has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as hardware synthesis, are becoming limiting factors in the rapid iteration of designs. To mitigate these emerging constraints, multiple efforts have been undertaken to develop an ML-based surrogate model that estimates resource usage of ML accelerator architectures. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of over 680,000 fully connected and convolutional neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, and the average performance across a subset of the dataset. Additionally, we introduce GNN- and transformer-based surrogate models that predict latency and resources for ML accelerators. We present the architecture and performance of the models and find that the models generally predict latency and resources for the 75th percentile within several percent of the synthesized resources on the synthetic test dataset.

Förderung

  • U.S. Department of Energy, Office of Science, Office of High Energy Physics
  • U.S. Department of Energy, Office of Science, Office of Workforce Development for Teachers and Scientists (WDTS), Science Undergraduate Laboratory Internships…
  • National Science Foundation
  • University of California Office of the President
  • University of California San Diego, California Institute for Telecommunications and Information Technology / Qualcomm Institute
  • Fermi Research Alliance, LLC, U.S. Department of Energy (DOE), Office of Science, Office of High Energy Physics
  • U.S. Department of Energy (DOE), Early Career Research Program
  • U.S. Department of Energy

Zitieren

APA

Hawks, B., Weitz, J., Demler, D., Tame-Narvaez, K., Plotnikov, D., Rahimifar, M. M., Rahali, H. E., Therrien, A. C., Sproule, D., Khoda, E. E., Smith, K. A., Marroquin, R., Guglielmo, G. D., Tran, N., Duarte, J., & Loncar, V. (2026). wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation. ACM Transactions on Reconfigurable Technology and Systems, 19(2), 1-29. https://doi.org/10.1145/3787490

Vancouver

Hawks B, Weitz J, Demler D, Tame-Narvaez K, Plotnikov D, Rahimifar MM, et al. wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation. ACM Transactions on Reconfigurable Technology and Systems. 2026;19(2):1-29. doi:10.1145/3787490

BibTeX
@article{Hawks2026,
  author = {Hawks, Benjamin and Weitz, Jason and Demler, Dmitri and Tame-Narvaez, Karla and Plotnikov, Dennis and Rahimifar, Mohammad Mehdi and Rahali, Hamza Ezzaoui and Therrien, Audrey C. and Sproule, Donovan and Khoda, Elham E. and Smith, Keegan A. and Marroquin, Russell and Guglielmo, Giuseppe Di and Tran, Nhan and Duarte, Javier and Loncar, Vladimir},
  title = {wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation},
  journal = {ACM Transactions on Reconfigurable Technology and Systems},
  year = {2026},
  volume = {19},
  number = {2},
  pages = {1--29},
  doi = {10.1145/3787490}
}
Kostenlos starten →